Abdelhafid Bouhraoua and M.E.S El-Rabaa

Slides:



Advertisements
Similar presentations
A Novel 3D Layer-Multiplexed On-Chip Network
Advertisements

Presentation of Designing Efficient Irregular Networks for Heterogeneous Systems-on-Chip by Christian Neeb and Norbert Wehn and Workload Driven Synthesis.
Flattened Butterfly Topology for On-Chip Networks John Kim, James Balfour, and William J. Dally Presented by Jun Pang.
REAL-TIME COMMUNICATION ANALYSIS FOR NOCS WITH WORMHOLE SWITCHING Presented by Sina Gholamian, 1 09/11/2011.
Chapter 8 Hardware Conventional Computer Hardware Architecture.
King Fahd University of Petroleum and Minerals CCSE – COESOC 2006 – Tampere, Nov. 2006Abdelhafid Bouhraoua A High Throughput Network-on-Chip Architecture.
What's inside a router? We have yet to consider the switching function of a router - the actual transfer of datagrams from a router's incoming links to.
Packet-Switched vs. Time-Multiplexed FPGA Overlay Networks Kapre et. al RC Reading Group – 3/29/2006 Presenter: Ilya Tabakh.
Network based System on Chip Part A Performed by: Medvedev Alexey Supervisor: Walter Isaschar (Zigmond) Winter-Spring 2006.
Chapter 10 Switching Fabrics. Outline Physical Interconnection Physical box with backplane Individual blades plug into backplane slots Each blade contains.
King Fahd University of Petroleum and Minerals CCSE – COESOC 2006 – Tampere, Nov. 2006Abdelhafid Bouhraoua A High Throughput Network-on-Chip Architecture.
1 Lecture 24: Interconnection Networks Topics: communication latency, centralized and decentralized switches (Sections 8.1 – 8.5)
Issues in System-Level Direct Networks Jason D. Bakos.
1 Lecture 25: Interconnection Networks Topics: communication latency, centralized and decentralized switches, routing, deadlocks (Appendix E) Review session,
Network-on-Chip: Communication Synthesis Department of Computer Science Texas A&M University.
Performance and Power Efficient On-Chip Communication Using Adaptive Virtual Point-to-Point Connections M. Modarressi, H. Sarbazi-Azad, and A. Tavakkol.
Approaching Ideal NoC Latency with Pre-Configured Routes George Michelogiannakis, Dionisios Pnevmatikatos and Manolis Katevenis Institute of Computer Science.
High Performance Embedded Computing © 2007 Elsevier Lecture 16: Interconnection Networks Embedded Computing Systems Mikko Lipasti, adapted from M. Schulte.
1 The Turn Model for Adaptive Routing. 2 Summary Introduction to Direct Networks. Deadlocks in Wormhole Routing. System Model. Partially Adaptive Routing.
Interconnect Networks
On-Chip Networks and Testing
ATM SWITCHING. SWITCHING A Switch is a network element that transfer packet from Input port to output port. A Switch is a network element that transfer.
Connectivity Devices Hakim S. ADICHE, MSc
High-Level Interconnect Architectures for FPGAs An investigation into network-based interconnect systems for existing and future FPGA architectures Nick.
High-Level Interconnect Architectures for FPGAs Nick Barrow-Williams.
1 Dynamic Interconnection Networks Miodrag Bolic.
1 Message passing architectures and routing CEG 4131 Computer Architecture III Miodrag Bolic Material for these slides is taken from the book: W. Dally,
Anshul Kumar, CSE IITD CSL718 : Multiprocessors Interconnection Mechanisms Performance Models 20 th April, 2006.
CS 8501 Networks-on-Chip (NoCs) Lukasz Szafaryn 15 FEB 10.
RF network in SoC1 SoC Test Architecture with RF/Wireless Connectivity 1. D. Zhao, S. Upadhyaya, M. Margala, “A new SoC test architecture with RF/wireless.
Anshul Kumar, CSE IITD ECE729 : Advanced Computer Architecture Lecture 27, 28: Interconnection Mechanisms In Multiprocessors 29 th, 31 st March, 2010.
Interconnect Networks Basics. Generic parallel/distributed system architecture On-chip interconnects (manycore processor) Off-chip interconnects (clusters.
MASCON: A Single IC Solution to ATM Multi-Channel Switching With Embedded Multicasting Ali Mohammad Zareh Bidoki April 2002.
Virtual-Channel Flow Control William J. Dally
Spring 2000CS 4611 Router Construction Outline Switched Fabrics IP Routers Extensible (Active) Routers.
Univ. of TehranIntroduction to Computer Network1 An Introduction to Computer Networks University of Tehran Dept. of EE and Computer Engineering By: Dr.
Univ. of TehranIntroduction to Computer Network1 An Introduction to Computer Networks University of Tehran Dept. of EE and Computer Engineering By: Dr.
Runtime Reconfigurable Network-on- chips for FPGA-based systems Mugdha Puranik Department of Electrical and Computer Engineering
McGraw-Hill©The McGraw-Hill Companies, Inc., 2000 Muhammad Waseem Iqbal Lecture # 20 Data Communication.
Graciela Perera Department of Computer Science and Information Systems Slide 1 of 18 INTRODUCTION NETWORKING CONCEPTS AND ADMINISTRATION CSIS 3723 Graciela.
Mohamed Abdelfattah Vaughn Betz
Fang Fang James C. Hoe Markus Püschel Smarahara Misra
Overview Parallel Processing Pipelining
Interconnect Networks
Dynamic connection system
A Closer Look at Instruction Set Architectures
Lecture 23: Interconnection Networks
Pablo Abad, Pablo Prieto, Valentin Puente, Jose-Angel Gregorio
Addressing: Router Design
Azeddien M. Sllame, Amani Hasan Abdelkader
Cache Memory Presentation I
Chapter 3 Part 3 Switching and Bridging
Approaching Ideal NoC Latency with Pre-Configured Routes
Deadlock Free Hardware Router with Dynamic Arbiter
Israel Cidon, Ran Ginosar and Avinoam Kolodny
Switching, routing, and flow control in interconnection networks
Overview of Computer Architecture and Organization
PRESENTATION COMPUTER NETWORKS
Router Construction Outline Switched Fabrics IP Routers
High Performance Computing & Bioinformatics Part 2 Dr. Imad Mahgoub
Advanced Computer Architecture 5MD00 / 5Z032 Multi-Processing 2
Low-Latency Virtual-Channel Routers for On-Chip Networks Robert Mullins, Andrew West, Simon Moore Presented by Sailesh Kumar.
EE 122: Lecture 7 Ion Stoica September 18, 2001.
Lecture: Interconnection Networks
Network-on-Chip Programmable Platform in Versal™ ACAP Architecture
Chapter 3 Part 3 Switching and Bridging
Advanced Computer and Parallel Processing
Switching, routing, and flow control in interconnection networks
MACS: A Minimal Adaptive Routing Circuit Switched Architecture for Scalable and Parametric NoCs Rohit Kumar Dr. Ann Gordon-Ross Introduction MACS: A.
Multiprocessors and Multi-computers
Presentation transcript:

A High Throughput Network-on-Chip Architecture for System-on-Chip Interconnect Abdelhafid Bouhraoua and M.E.S El-Rabaa Computer Engineering Department (COE) College of Computer Science and Engineering (CCSE) King Fahd University of Petroleum and Minerals (KFUPM) Dhahran, Eastern Province, Saudi Arabia

Outline Overview and Motivation Fat Tree Network Properties Modified Fat Tree Router Architecture Performance Evaluation Conclusion

Outline Overview and Motivation Fat Tree Network Properties Modified Fat Tree Router Architecture Performance Evaluation Conclusion

Semiconductor Industry Future Chip Complexity: 100M – 3B. ASIC Methodology Not Suitable RTL  Synthesis  Back End Impossible to handle Full RTL Design for the whole project SoC Era: IP Block Based Design Methodology

SoC Constraints Very Short Time-To-Market Very Short Lifecycle Compressed Schedule Very Short Lifecycle Low Development Cost Small Team High Complexity Available Silicon Resources to Produce Cost-Effective Highly Integrated SoCs. Broad Range of IP Blocks Impossibility to know them all

SoC Methodology Main Task: Interconnection of The IP Blocks System Level Integration Data Formatting and Conversion Protocol/Control Interfacing Interconnection Level Integration Signal (Polarity and Trigger) Interfacing Data Transfer Interfacing Wire Interconnect and Back-end Integration

Networks-on-Chips “Route Packets NOT Wires”, William J. Dally Idea: Build a Complete on-Chip Network Unified Communication Model (Similar to OSI Stack) No Ad-hoc Effort Standardized Interfacing (May be provided by IP Vendors) Unified Network Elements (Routers, Link Interfaces) No Design required by the SoC Teams Flexible Interconnect and Reduced Global Wiring

NoC Requirements Performance Overhead Adaptivity Complexity How fast packets are moved across the network? How much traffic is carried at the same time and for how long? Overhead How Big is its required Size (in Gates) ? Adaptivity Does it Adapt Easily to new Designs ? Complexity How Easy is Interfacing to it ?

Previous Work Majority directly derived from other research (Interconnection Networks for Parallel Architectures) Router architectures directly derived from inter-chip architectures where the routers were implemented on a single chip  substantial overhead. Reproduce what has been learned in the area of inter-chip networks, Focus on the router architecture alone to achieve certain goals in latency Circuit switching techniques introduced to provide a certain guarantee for the latency. Did not fully take advantage of the fact that the network is on-chip where the main gain is no-pin limitation. Added complexity to achieve guaranteed latency is an overkill in the on-chip context.

Most Straightforward  Crossbar Which Network? Most Straightforward  Crossbar Good Throughput (maxes at 66%) Non Scalable (Quadratic) Complexity Of Implementation for Higher Number of I/Os.

2-D Mesh Very Popular Topology in NoCs. Very High Constraints Very Suitable for the 2D nature of Chip Floorplanning (Tiling) Very High Constraints Inefficient routing algorithms (deadlock-free by construction) Efficient routing algorithms (Complex implementation) Poor performance: Saturation reached at 30 %.

Analysis Low throughput. Means: latency cannot be guaranteed above the maximum throughput levels Low throughput cause by contention over the output ports of routers among several incoming packets Cannot prevent contention from happening. Contention makes router architectures more complex because they need to integrate buffering and prioritization logic. Routers that implement both packet and circuit switching makes the architecture even more complex.

Methodology Take advantage of the On-Chip Context: Design frozen before tape out No internal IO limitations Aim for a High Throughput Architecture Circuitry used at 30% of its maximum is NOT an optimal Solution (Clock frequency, power). Reduced router size Integrate a large number of routers Wormhole routing vs. Store and Forward Reduce required buffers in routers

Fat Tree What topology resembles a crossbar? Banyans or Multistage Interconnection Networks. R C Bidirectional multistage or folded multistage networks Bidirectional multistage are two entities: The Fat Tree (FT) The butterfly. Fat Tree better than butterfly (previous work) n+1 Stages (or rows) Size is Routers = n x 2n Clients = 2n+1 Diameter = 2logk + 1; n = log k

Outline Overview and Motivation Fat Tree Network Properties Modified Fat Tree Router Architecture Performance Evaluation Conclusion

Routing reduced to routing in a binary tree. Routing in Fat Tree Routing reduced to routing in a binary tree. Binary Trees Router UP LEFT RIGHT Three Routing Directions UP RIGHT LEFT

Routing in Fat Tree Matrix n rows x 2(n-1) columns. Router (r,c) r : row index (rows are indexed from 0 to n-1) c: column index (columns are indexed from 0 to 2(n+1) -1) Size of the clients’ address space reachable using the downside ports is equal to 2r It is always a continuous interval of addresses of the form [l, u[. Router (r,c) [0, l[ U [u, 2n+1 -1] [l, l+2r-1[ [l+2r-1, u[ Lower bound l : smallest address reached from the router (r,c). Smallest address within the range obtained by clearing the lowest r bits of the column c. l = (c/2r) x 2r. Upper bound u: largest address reached from the router (r,c). Largest address obtained by adding 2r to the lower bound l. u = l+ 2r.

Routing In Fat Tree Routing UP: Adaptive Routing Down: Deterministic “Summit” Routers R C Alternate Paths Routing UP: Adaptive Routing Down: Deterministic

Outline Overview and Motivation Fat Tree Network Properties Modified Fat Tree Router Architecture Performance Evaluation Conclusion

Contention in Fat Tree UP LEFT RIGHT on the way down Many Choices for Going UP LEFT RIGHT Packets coming from the UP links are never routed up Only packets coming from the bottom links are routed up. Since the number of UP links is equal to the number of bottom links, there cannot be any contention when routing up. Contention occurs only when going down. Bottom links are split in RIGHT and LEFT links, deterministic routing of packets will lead to contention.

Modified Fat Tree Doubling of downward links eliminates contention C R

Outline Overview and Motivation Fat Tree Network Properties Modified Fat Tree Router Architecture Performance Evaluation Conclusion

Router Architecture No Crossbar No Buffers (Pushed to the Clients) Left Inputs Right k 2k + 2 No Crossbar No Buffers (Pushed to the Clients) Every downstream input simultaneously connected to two outputs. Contention eliminated between the inputs going downstream. Number of outputs is 2k+2 for k inputs (case of when the router is a summit) Router models differ from each other only by two items: Number of input and output ports on the down link Routing function constants (r,c)

Routing Circuitry All network elements are constants and frozen at design time. All lower bound and upper bound values, used to generate the routing functions, are constants for each router. These constants are entered as inputs into the routing function Routing Function implemented using comparators. Constants needed by the routing function are: l L = l + 2r-1 u Address ≥ < A B l L u LEFT RIGHT UP

Client Interface Buffers pushed to the Client Interfaces Each incoming link is terminated with a FIFO memory. The different FIFO memories connected to the client through a single shared bus. Up Link Down Links (from router) FIFO FIFO FIFO FIFO FIFO Client/IP Block Bus can be wider to perform data transfers faster than what is received in the FIFOs. The size of FIFOs customizable by design team according to the specifications

Outline Overview and Motivation Fat Tree Network Properties Modified Fat Tree Router Architecture Performance Evaluation Conclusion

Simulation Conditions Uniform Traffic Generation Uniform Distribution of Destinations Traffic Rate constant fraction of Maximum Link Bandwidth Variable Packet Size (within a predetermined range; eg. 64 bytes +/- 10%) Simulation Platform: Cycle-based C-based. Developed for this purpose

Throughput More than 90% Throughput achieved Compare with Regular Fat Tree

Latency Latency has linear progression Large component of Latency spent in Receiver’s FIFOs

Buffer-less architecture less costly Area and Speed Buffer-less architecture less costly

Client Buffer Utilization Buffers pushed to the client interfaces. Considerable number of buffer lanes is necessary for every client interface. Simulations shows a linear progression of the maximum number of lanes used during operation. Obtained figures are an order of magnitude lower than the number required by the architecture. Number of buffer lanes in the client interface can be tailored to suit the class of applications at hand while reducing buffering area.

Outline Overview and Motivation Fat Tree Network Properties Modified Fat Tree Router Architecture Performance Evaluation Conclusion

Conclusion A contention-free modified FT architecture is proposed. Proposed architecture achieves maximum theoretical throughput and has smaller latency than conventional FTs. Latency increases linearly with input load. Achieved performance is actual performance using a contention-free network. The area of the network is kept small because of the absence of buffers in the router architecture. Number of buffer lanes in the client interfaces can be tailored for a specific platform to suit the class of applications at hand while reducing buffering area.